Learning meshless parameterization with graph convolutional neural networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Learning meshless parameterization with graph convolutional neural networks

Abstract

This paper proposes a deep learning approach for parameterizing an unorganized or scattered point cloud in R 3 with graph convolutional neural networks. It builds upon a graph convolutional neural network that predicts the weights (called parameterization weights) of certain convex combinations that lead to a mapping of the 3D points into a planar parameter domain. First, we compute a radius neighbours graph that yields proximity information to each 3D point in the cloud. This radius graph is then converted to its line graph, which encodes edge adjacencies, and is equipped with appropriate weights. The line graph is used as input to a graph convolutional neural network trained to predict optimal parameterizations. The proposed model outperforms closed-form choices of the parameterization weights and produces high quality parameterizations for surface reconstruction schemes.
Fichier principal
Vignette du fichier
157.pdf (3.89 Mo) Télécharger le fichier
Vignette du fichier
face.png (251.94 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-04142674 , version 1 (27-06-2023)

Licence

Attribution

Identifiers

Cite

Carlotta Giannelli, Sofia Imperatore, Angelos Mantzaflaris, Felix Scholz. Learning meshless parameterization with graph convolutional neural networks. 2023 World Conference on Smart Trends in Systems, Security and Sustainability, Aug 2023, London, United Kingdom. pp.375-387, ⟨10.1007/978-981-99-7886-1_32⟩. ⟨hal-04142674⟩
151 View
94 Download

Altmetric

Share

Gmail Facebook X LinkedIn More